scientific-visualization

Meta-skill for publication-ready figures. Use when creating journal submission figures requiring multi-panel layouts, significance annotations, error bars, colorblind-safe palettes, and specific journal formatting (Nature, Science, Cell). Orchestrates matplotlib/seaborn/plotly with publication styles. For quick exploration use seaborn or plotly directly.

1.36x

Quality

75%

Does it follow best practices?

Impact

93%

1.36x

Average score across 6 eval scenarios

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./scientific-skills/scientific-visualization/SKILL.md

Quality

Discovery

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This is an excellent skill description that clearly defines a specific niche (publication-ready scientific figures), lists concrete capabilities, includes natural trigger terms researchers would use, and explicitly delineates when to use it versus alternatives. The negative boundary statement is a particularly strong addition that helps disambiguate from general plotting skills.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: multi-panel layouts, significance annotations, error bars, colorblind-safe palettes, and specific journal formatting. Also names concrete tools (matplotlib/seaborn/plotly) and concrete journals (Nature, Science, Cell).	3 / 3
Completeness	Clearly answers both 'what' (creating publication-ready figures with multi-panel layouts, annotations, error bars, palettes, journal formatting) and 'when' (explicit 'Use when creating journal submission figures requiring...' clause). Also includes a helpful negative trigger ('For quick exploration use seaborn or plotly directly').	3 / 3
Trigger Term Quality	Excellent coverage of natural terms a user would say: 'publication-ready figures', 'journal submission', 'multi-panel layouts', 'significance annotations', 'error bars', 'colorblind-safe', and specific journal names (Nature, Science, Cell). These are highly natural terms researchers would use.	3 / 3
Distinctiveness Conflict Risk	Highly distinctive niche targeting publication-ready scientific figures with journal-specific formatting. The explicit negative boundary ('For quick exploration use seaborn or plotly directly') further reduces conflict risk with general plotting skills.	3 / 3
	Total	12 / 12 Passed

Implementation

50%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The skill is highly actionable with excellent executable code examples and concrete specifications, but it is severely bloated. The seaborn section alone could be its own reference document, and there is significant repetition of patterns (color palettes, export commands, despine calls) throughout. The content would benefit greatly from aggressive trimming and moving detailed library-specific content to reference files.

Suggestions

Move the entire seaborn section (~200 lines) to a separate reference file and replace with a 5-10 line summary pointing to it, since the skill already references scientific-packages/seaborn/SKILL.md

Eliminate repeated code patterns—colorblind palette setup, save_publication_figure calls, and sns.despine() appear 5+ times each; show each pattern once and reference it

Remove explanatory text that describes what Claude already knows (e.g., 'Seaborn provides a high-level, dataset-oriented interface for statistical graphics...', axes-level vs figure-level function explanations)

Add explicit validation/feedback loops to the workflow: e.g., 'Run colorblind simulation check → if fails, adjust palette → re-check' rather than just listing 'Verify' as a step

Dimension	Reasoning	Score
Conciseness	This skill is extremely verbose at ~500+ lines. The seaborn section alone is massive and largely duplicates information Claude already knows. Concepts like what seaborn is, axes-level vs figure-level functions, and basic plotting patterns are well within Claude's existing knowledge. There is enormous repetition—colorblind palettes, despine(), and export patterns are shown 5+ times each.	1 / 3
Actionability	The skill provides fully executable, copy-paste ready code examples throughout. Concrete commands, specific hex color values, exact DPI numbers, journal dimension specifications in mm, and working Python code with proper imports are all present.	3 / 3
Workflow Clarity	The workflow summary at the end provides a clear 6-step sequence with code snippets, and the final checklist is useful. However, there are no explicit validation/feedback loops—step 4 says 'Verify' but only checks size, not whether the figure actually renders correctly or whether colors pass accessibility testing. The 'Fix an Existing Figure' task is a checklist without error recovery steps.	2 / 3
Progressive Disclosure	References to external files (publication_guidelines.md, color_palettes.md, journal_requirements.md, matplotlib_examples.md) are well-signaled and organized. However, the massive inline seaborn section (~200 lines) should clearly be in a separate reference file rather than inline, and much content that is referenced externally is also duplicated inline.	2 / 3
	Total	8 / 12 Passed

Validation

81%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 9 / 11 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (778 lines); consider splitting into references/ and linking	Warning
metadata_version	'metadata.version' is missing	Warning

	Total	9 / 11 Passed

Repository: K-Dense-AI/claude-scientific-skills
Commit: 086de41

Reviewed: about 17 hours ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.